Hierarchical Hierarchical Annotation Annotation of Medical Images of Medical Images Ivica Dimitrovski 1 , Dragi Kocev 2 , Suzana Loškovska 1 , Sašo Džeroski 2 1 Department of Computer Science, Faculty of Electrical Engineering and Information Technologies, Skopje, Macedonia 2 Department of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia
23
Embed
Hierarchical Annotation of Medical Images Ivica Dimitrovski 1, Dragi Kocev 2, Suzana Loškovska 1, Sašo Džeroski 2 1 Department of Computer Science, Faculty.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Hierarchical Annotation Hierarchical Annotation of Medical Imagesof Medical Images
1Department of Computer Science, Faculty of Electrical Engineering and Information Technologies, Skopje, Macedonia
2Department of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia
OverviewOverview
• Introduction and problem
definition
• Feature extraction
– Edge Histogram Descriptor (EHD)
• Classifier
– PCTs for HMLC
• Experiments and results
• Conclusions and future work
IntroductionIntroduction
• The amount of medical images is constantly growing
• The cost of manually annotating these images is very high– automatic image annotation algorithms to perform
the task reliably
• Feature extraction from images• Classifier to distinguish between different
classes• Application: Multilingual image annotations and
DICOM standard header corrections
IRMA codeIRMA code
• IRMA coding system: Four axes marked with {0, …, 9, a, …, z}– T (Technical): image modality– D (Directional): body orientation– A (Anatomical): body region– B (Biological): biological system
• IRMA code: TTTT – DDD – AAA – BBB• The code is strictly hierarchical
– Example:2 cardiovascular system
21 cardiovascular system; heart
216 cardiovascular system; heart; aortic valve
IRMA code - exampleIRMA code - example
• IRMA code: 1123-211-520-3a0
– 1123 (x-ray, projection radiography, analog, high energy)
– 211 (sagittal, left lateral descubitus, inspiration)
• Classifier– Number of classifiers: 100 un-pruned trees– Random Forests Feature Subset Size: 7 (log)
• Comparison of the performance of a single tree and an ensemble– Precision-Recall (PR) curves - “area under the PR
curve” (AUPRC)– 10 fold cross-validation
• Two scenarios1) Each axis is an dataset (4 in total)
2) Single dataset for all axes
Results per axisResults per axis
Results per axisResults per axis
Results for all axesResults for all axes
DiscussionDiscussion
• Increase of the predictive performance with ensembles compared to a single tree
• Excellent performance for axes T and B (AUPRC of 0.9994 and 0.9862) – The hierarchies for axes T and B contain only few nodes (9 and
27, respectively)
• The classifiers for axes A and D have high predictive performance (AUPRC of 0.8264 and 0.9064) – The hierarchies for axes A and D contain 110 and 36 nodes,
respectively
• Predicting the complete hierarchy at-once yields improvements
SummarySummary
• Medical image annotation using Hierarchical Multi-Label Classification (HMLC)
• Local Edge Histogram Descriptor (EHD) to represent gray-scale radiological (X-Ray) images
• Images annotated with IRMA code
• Ensembles of PCTs for HMLC as classifier
Future workFuture work
• Other algorithms for feature extraction:– SIFT, TAMURA, Scale, Color Histogram…
• Combination of the features obtained from different techniques:– Each technique captures different aspects of an image
• Extension of the classification algorithm:– Distance measures for hierarchies– Learning under covariate shift